【CCS 2023 杰出论文】为他人做嫁衣裳:Web 3.0中的投票治理及其安全
本次分享的论文为CCS 2023 杰出论文。该项研究以Web 3.0时代中的真实事件为背景,深入探讨了去中心化的DPoS(代理权益证明)区块链系统在抵御恶意接管方面的能力。
A few days ago Riley Goodside posted about an interesting discovery on how an LLM prompt injection can happen via invisible instructions in pasted text. This works by using a special set of Unicode code points from the Tags Unicode Block.
The proof-of-concept showed how a simple text contained invisible instructions that caused ChatGPT to invoke DALL-E to create an image.
Hidden Instructions for LLMsThe meaning of these “Tags” seems to have gone through quite some churn, from language tags to eventually being repurposed for some emojis.